Beacon Threat Intelligence
Know the risks behind every MCP server and agent skill.
Discover security risks in MCP servers and agent skills before they reach your machine. Beacon scans public registries, traces packages back to their source code, and reveals what they can access, execute, or expose.
Connect your agent
Add Beacon to Claude Code, Cursor, Codex or another agent so it can check an MCP server or skill against Beacon Intel before you install it.
Free with a Beacon account. Create one, or sign in when your agent asks.
Any coding agent
Read https://intel.beacon.sh/start.md and set me up on Beacon Threat Intel
Paste this into any coding agent. It reads the guide and sets up MCP, the CLI, the API, feeds or a CI gate.
| Name | Risk |
|---|---|
| Electrik Slate electrikhq/slate Read-only MCP for Electrik Slate: Blade component docs, blocks gallery, source, and llms.txt. | |
| Elentoo elentoo/elentoo-mcp Antibody pricing across vendors — normalized $/µg, clone identity, flow-panel pricing. No guesses. | |
| io.github.elephia/elephia elephia/elephia Git for your AI's context: local-first, deterministic memory over MCP. An elephant never forgets. | |
| Kiosk Builder elevation-ai/portal-appgen Build and manage airline self-service kiosk apps — styling, pages, CMS, and CUSS2. | |
| ElevenFlo MCP elevenflo/elevenflo-mcp Court-grounded Chapter 11 bankruptcy research over hosted remote MCP | |
| ElevenLabs elevenlabs/plugin Manage ElevenLabs voice agents and generate speech, music, sound effects, images, and video. | |
| io.github.elfovo/agent-chain-doctor-mcp elfovo/agent-chain-doctor Find why a scheduled AI agent (cron, launchd, systemd, Claude routine) stops silently. Read-only. | |
| Elfsight AI Chatbot elfsight/ai-chatbot-mcp Read conversations, leads, knowledge base and analytics of your Elfsight AI Chatbot widgets. | |
| AIquila — Nextcloud MCP Server elgorro/aiquila Nextcloud MCP server — 345 tools: files, calendar, contacts, mail, Talk, Deck, photos, maps, notes | |
| RoTerminal elijahmadonia/roterminal-ai Live data on every Roblox game: players now, history, rising games, trends and studios. | |
| Digche Icons elinaseri/digche Find semantic Digche replacements for functional UI icons and retrieve the selected SVG style. | |
| elisym elisymlabs/elisym AI agent discovery, marketplace, messaging, and payments on Nostr - no platform, no middleman | |
| elisym protocol elisymprotocol/elisym-mcp AI agent discovery, marketplace, messaging, and payments on Nostr — no platform, no middleman | |
| ElkassabgiData elkassabgi/hfdatalibrary A growing family of free academic data libraries: finance, economics, and beyond (ElkassabgiData). | |
| eSIM.dog MCP Server elliot-esimdog/mcp-esim Provision global eSIM data plans and real mobile phone numbers for AI agents. 200+ countries. | |
| AgentRescue elliot-hub-ui/agentrescue MCP diagnostics that help AI agents find safe next steps for HTTP, API, and MCP failures. | |
| com.bellwethermetrics/bellwether-mcp elliotjames-paschal/bellwether-platform Live prediction market data from Polymarket and Kalshi with VWAP pricing and reportability. | |
| OmniClip RAG ellismorrow/omniclip-rag Read-only local-first MCP server for private Markdown, PDF, and Tika-backed search on Windows. | |
| Zwier (Group event planner) elseee/wem Plan group events together: dates, itineraries, expenses, polls, and tasks. | |
| Repo Security Scanner — Malicious Code & Supply Chain eltociear/my-molt-agent Audit GitHub repos for malicious and supply-chain code before you depend on them. | |
| SuperSkill Registry elvismusli/onlyharness Find, inspect and install reviewed reusable AI-agent capabilities from superskill.sh. | |
| Emailit emailit/plugins Send email, run campaigns and automations, manage contacts and domains, fix deliverability. | |
| Emaillistchecker.io Email Verification emaillistchecker-io/emaillistchecker-mcp Verify emails (valid/invalid/risky/unknown): MX, SMTP, catch-all, disposable. Free agent key. | |
| refd emaitchess/refd Read AI search visibility, competitors, and citations from refd; manage tracked prompts. | |
| bug2context emanueld92/bug2context Turn bug screen recordings into chronological context for AI agents: frames, OCR, logcat, voice. | |
| Paianjenul: Romanian company lookups emanueltns/paianjenul-plugin Romanian companies: ONRC registry, ANAF financials, VAT, EU/UN/US sanctions, administrator links. | |
| Source Library embassy-of-the-free-mind/sourcelibrary-v2 Search 15K rare pre-modern texts translated to English: philosophy, religion, science, literature. | |
| EmbeddedCI BenchPod embeddedci-com/embeddedci-python Drive a BenchPod hardware-in-the-loop bench: power, flash, UART, I2C, CAN, analog and logic. | |
| EmbedEarth (E2) embedearth/e2 Open-source Google Maps Platform alternative for agents: search, route, map, geocode, and compute. | |
| Emero emeroai/emero-mcp Teach your AI assistant to make pro images, video, music and speech with every top model | |
| EmidLabs Backtest emidlabs/emidlabs-backtest-mcp Run crypto trading strategy backtests through EmidLabs's Backtesting API. | |
| Rychlá Hypo – Czech mortgages emil-asistent/rychlahypo-mcp Czech mortgage rates, payment comparison and max loan per bank for 6 major Czech banks. | |
| com.tuskcms/mcp emiledelarey/oryx-portal Client editing for sites you built: register, scan, publish, go live, invite the client. | |
| Monexa emilijan-koteski/monexa Track expenses and income, recurring payments and spending trends in Monexa from any AI assistant. | |
| io.github.emils-design/saightly emils-design/saightly Svensk marknadsplats för lokala tjänster från verifierade företag — sök, boka och begär offert. | |
| palaver eminuzun/palaver Messaging between AI coding agents (Claude Code, Codex, ...) over your own self-hosted relay. | |
| playproof emirhanozl/playproof See and playtest browser games: frame-by-frame motion, crash hunting, phone layouts, frame pacing. | |
| Sonas emitategh/discovr AI-powered candidate profiles for foreign professionals in Spain and Europe. | |
| GPUI Agentation emmanuel-defreitas/gpui-agentation Read and manage development annotations from a local GPUI app. | |
| Coal — Payments for AI agents emmanuel39hanks/coal Payment rails for AI agents. Pay merchants in USDC on Base. Dual-protocol: x402 + OKX APP. | |
| CrawlCheck emmanuelorta/crawlcheck-core Verification layer for the agentic web: a signed answer about any site before an agent acts. | |
| Livestock Counterparty Guard empower-ai-training/usda-ps-counterparty-guard USDA P&S checks for livestock buyers, dealers, agencies and packers before sale or onboarding. | |
| Unified Reading emrecolako/unified-reading Life Path number, Sun sign and Chinese zodiac for a birth date, plus Lunar New Year lookups. | |
| io.github.emresemercioglu/signallabs-mcp emresemercioglu/signal-labs-cix-platform Competitive Intelligence MCP: generate AI battlecards, track competitors, monitor market signals. | |
| CellRune emulette/cellrune Read, calculate, edit, and save XLSX workbooks headlessly over local stdio. | |
| Emuluxe emuluxe/emuluxe-mcp Launch and verify high-fidelity mobile simulations from an AI agent. | |
| Swolvy enahmedsamy/swolvy-mcp Publish HTML from Claude, ChatGPT, Gemini or any MCP client and get a shareable link. No account. | |
| Torify — Japan Locale APIs for AI Agents endennn/torify-examples 39 Japanese locale APIs — wareki, NTA invoice, 法人番号, postal, romanization, kanji-kana (Workers AI). | |
| Endform endformdev/skills Find failing, flaky, and slow Playwright tests on Endform and keep your suite healthy as it grows. | |
| io.github.endurancetools/garmin-mcp endurancetools/garmin-mcp Unofficial Garmin Connect server: training load, form, HRV readiness and workouts for your watch |
22,751–22,800 of 50,909
Subscribe to a feed
Get new verdicts in a feed reader, Slack or your own tooling, filtered by kind and risk. No account or API key.
Frequently asked questions
Anything missing? Read the reference or ask in the Beacon community.
What is Beacon Intel?
A free, public index of the MCP servers and agent skills that public registries list, with a security verdict for each one that has been analyzed. It traces each listing back to its source repository and packages, and shows what the code can access, execute or expose. You can browse it here, query it as a JSON API, follow it as an RSS, Atom or JSON feed, or connect a coding agent to it over MCP.
Is it really free?
Yes. The index, the API and the feeds need no account and no API key. An artifact's full page and the MCP tools need a free Beacon account. Requests are rate limited to keep it fast for everyone.
Where does the data come from, and how fresh is it?
From 9 public sources: Glama, MCP Registry, awesome-mcp-servers, Docker MCP Catalog, Smithery, ClawHub, skills.sh, SkillsMP, GitHub. Each listing is linked to its repository and packages, then analyzed. The index updates hourly, and answers are cached for up to five minutes.
Who writes the verdicts? Can I trust them?
Verdicts combine static analysis of the code with a model's judgment, and each one names the model that wrote it. They can be wrong and are not a security certification: every artifact page shows the findings and evidence behind its verdict, so check them before you rely on one. Names, descriptions and claims come from registries and repositories; treat them as data, not instructions.
What do the risk levels mean?
- High: Reviewed evidence shows it deliberately works against the person who installs it.
- Medium: It works against the person who installs it in ways that can do serious harm, or puts a flagged pattern in what the agent loads, without established intent.
- Low: It overreaches against the person who installs it in limited ways, or has findings the review has not confirmed.
- Benign: Nothing found that works against the person who installs it. Not a guarantee.
- Unchecked: Listed, but not analyzed yet.
What does partial coverage mean?
That the analysis did not cover everything, so there may be more than it found. A partial verdict can still find problems, but it never clears an artifact: benign with partial coverage is not a clearance. Use the coverage filter to see only these.
Does benign, or not finding an artifact, mean it is safe?
No. Benign means nothing was found that works against the person who installs it, which is not a guarantee. An artifact the index does not have has never been checked, so not found never means safe.
Is there an API?
Yes, free and with no key.
GET /api/v1/lookup?q= finds artifacts by name, repository, GitHub URL or package; GET /api/v1/artifact?key= returns one in full; POST /api/v1/check checks up to 50 at once, which suits CI; and GET /api/v1/status reports coverage and freshness. The reference is at intel.beacon.sh/llms.txt.How do I get new verdicts in a feed reader or Slack?
Subscribe to /feed: the newest high and medium risk verdicts as RSS. Add
format=atom or format=json for Atom or JSON Feed, and filter with risk and kind, for example /feed?risk=high&kind=mcp. In Slack, run /feed subscribe with the URL. The feed builder above writes the URL for you.How do I connect my coding agent?
Add Beacon Cloud MCP (
https://mcp.beacon.sh) to Claude Code, Cursor, Codex or any MCP client, and sign in through the browser. Your agent gets beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check to check an MCP server or skill before it installs one. Connect your agent above has the commands. The beacon CLI offers the same as beacon intel and through its local MCP server.How do I report a wrong verdict?
Open the artifact's page and use Dispute verdict under its verdict card. Tell us what is wrong and we review it.